Andrew Birmingham is the editor-in-chief and publisher of Which-50. He is the former associate publisher of The Australian Financial Review and remains a contributing editor, and during his career he has reported on the Australian media, technology, finance, life science and related sectors over a period spanning 20 years. His work has been published by The AFR, The Australian, The Sydney Morning Herald, The Age, MIS, Computerworld, CIO, ARN, Network World, CRN Australia, and My Business.

Technologically, the 20-year jump from 2015 to 2035 will be huge. During that time some elements of our world will change beyond recognition while others will stay reassuringly (or disappointingly) familiar. Consider the 20 years to 2015. Back in 1995 we were in the early days of the internet, we worked in cubicles and our computers were chunky and powered by Windows 95. There were no touch screen phones or flat screen TVs; people laughed at the idea of reading electronic books, and watching a home movie meant loading a clunky cassette into your VCR.

Incremental learning from non-stationary data poses special challenges to the field of machine learning. Although new algorithms have been developed for this, assessment of results and comparison of behaviors are still open problems, mainly because evaluation metrics, adapted from more traditional tasks, can be ineffective in this context. Overall, there is a lack of common testing practices. This paper thus presents a testbed for incremental non-stationary learning algorithms, based on specially designed synthetic datasets. Also, test results are reported for some well-known algorithms to show that the proposed methodology is effective at characterizing their strengths and weaknesses. It is expected that this methodology will provide a common basis for evaluating future contributions in the field.

We introduce a novel generative formulation of deep probabilistic models implementing "soft" constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then characterize the posterior distribution over model and constraint parameters through stochastic variational inference. As a result, the proposed approach allows for accurate and scalable uncertainty quantification on the predictions and on all parameters. We demonstrate the application of equality constraints in the challenging problem of parameter inference in ordinary differential equation models, while we showcase the application of inequality constraints on the problem of monotonic regression of count data. The proposed approach is extensively tested in several experimental settings, leading to highly competitive results in challenging modeling applications, while offering high expressiveness, flexibility and scalability.

We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illustrate the potential of attentional word segmentation for language documentation.

Multiwinner voting rules are used to select a small representative subset of candidates or items from a larger set given the preferences of voters. However, if candidates have sensitive attributes such as gender or ethnicity (when selecting a committee), or specified types such as political leaning (when selecting a subset of news items), an algorithm that chooses a subset by optimizing a multiwinner voting rule may be unbalanced in its selection -- it may under or over represent a particular gender or political orientation in the examples above. We introduce an algorithmic framework for multiwinner voting problems when there is an additional requirement that the selected subset should be "fair" with respect to a given set of attributes. Our framework provides the flexibility to (1) specify fairness with respect to multiple, non-disjoint attributes (e.g., ethnicity and gender) and (2) specify a score function. We study the computational complexity of this constrained multiwinner voting problem for monotone and submodular score functions and present several approximation algorithms and matching hardness of approximation results for various attribute group structure and types of score functions. We also present simulations that suggest that adding fairness constraints may not affect the scores significantly when compared to the unconstrained case.

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a central capsule by tailoring a specific centripetal loss function. We also show how our network, named HitNet, is capable of synthesizing a representative sample of the images of a given class by including a reconstruction network. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. In addition, we introduce the possibility for HitNet, to adopt an alternative to the true target when needed by using the new concept of ghost capsules, which is used here to detect potentially mislabeled images in the training data.

The applications of image analytics are endless. Organizations are starting to realize the possibilities of how to extract value from unstructured data, such as images or video footage, to create a new and enticing customer experience within retail, entertainment, transportation and airport security, insurance claims, and more. Here are five image analytics applications that are unexpected, disruptive, and creative. On June 26th, I'll be talking about image analytics use cases at the Boston Area SAS Users Group in my Image Processing: Seeing the World through the Eyes of SAS Viya talk. Curious to know who attended the Royal Wedding?

We consider the problem of learning to play first-person shooter (FPS) video games using raw screen images as observations and keyboard inputs as actions. The high-dimensionality of the observations in this type of applications leads to prohibitive needs of training data for model-free methods, such as the deep Q-network (DQN), and its recurrent variant DRQN. Thus, recent works focused on learning low-dimensional representations that may reduce the need for data. This paper presents a new and efficient method for learning such representations. Salient segments of consecutive frames are detected from their optical flow, and clustered based on their feature descriptors. The clusters typically correspond to different discovered categories of objects. Segments detected in new frames are then classified based on their nearest clusters. Because only a few categories are relevant to a given task, the importance of a category is defined as the correlation between its occurrence and the agent's performance. The result is encoded as a vector indicating objects that are in the frame and their locations, and used as a side input to DRQN. Experiments on the game Doom provide a good evidence for the benefit of this approach.

The dominant, state-of-the-art collaborative filtering (CF) methods today mainly comprises neural models. In these models, deep neural networks, e.g.., multi-layered perceptrons (MLP), are often used to model nonlinear relationships between user and item representations. As opposed to shallow models (e.g., factorization-based models), deep models generally provide a greater extent of expressiveness, albeit at the expense of impaired/restricted information flow. Consequently, the performance of most neural CF models plateaus at 3-4 layers, with performance stagnating or even degrading when increasing the model depth. As such, the question of how to train really deep networks in the context of CF remains unclear. To this end, this paper proposes a new technique that enables training neural CF models all the way up to 20 layers and beyond. Our proposed approach utilizes a new hierarchical self-attention mechanism that learns introspective intra-feature similarity across all the hidden layers of a standard MLP model. All in all, our proposed architecture, SA-NCF (Self-Attentive Neural Collaborative Filtering) is a densely connected self-matching model that can be trained up to 24 layers without plateau-ing, achieving wide performance margins against its competitors. On several popular benchmark datasets, our proposed architecture achieves up to an absolute improvement of 23%-58% and 1.3x to 2.8x fold improvement in terms of nDCG@10 and Hit Ratio (HR@10) scores over several strong neural CF baselines.